arxiv
PublishedSeptember 14, 2026 at 4:00 AM
—neutral
Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampling
Publisher summary· verbatim
arXiv:2609.08981v2 Announce Type: replace Abstract: A growing body of work establishes that large language models are not mere statistical memorizers, but are capable of in-context learning: performing inference at test time using only examples provided in the prompt, without any parameter updates.
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivBenford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models7harxivEvidence-Aligned Local Composition of Discrete Experts for Sequence Restoration7harxivDynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model7harxivFEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data7hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗